© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9844
    Prev
    Next
    INDEX
    Explanations

    published or issued

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on mentions of publication or release metadata—verbs like “published,” “issued,” “released,” etc., often accompanied by years, dates, and “by.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     who
    -1.75
     porque
    -1.35
    be
    -1.33
     способствует
    -1.33
    koľvek
    -1.32
    ㋛
    -1.31
     Wednesday
    -1.30
     reasons
    -1.29
     والم
    -1.28
     perché
    -1.27
    POSITIVE LOGITS
     hukuman
    1.38
     dokter
    1.26
    denk
    1.25
     feitas
    1.24
     muncul
    1.24
     meninggal
    1.23
    Aes
    1.23
    JMS
    1.23
    CPA
    1.21
     vermelha
    1.20
    Activations Density 0.074%

    No Known Activations